© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10927
    Prev
    Next
    INDEX
    Explanations

    Names with trailing suffixes or titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĸ³
    -0.23
    åīĤ
    -0.20
    å¾Ĥ
    -0.19
    éĻŁ
    -0.19
    erval
    -0.19
    èŁł
    -0.19
    craft
    -0.19
    Ñīа
    -0.19
     Müd
    -0.18
    ç¬ı
    -0.18
    POSITIVE LOGITS
    -G
    0.23
    -D
    0.21
     iNdEx
    0.20
    _IList
    0.20
    -C
    0.20
    -On
    0.20
    	RTLR
    0.20
    ornings
    0.20
    âĢIJ
    0.19
    _equalTo
    0.19
    Activations Density 0.091%

    No Known Activations